SAN FRANCISCO - Google announced on Wednesday the launch of Gemini CLI, an agentic artificial intelligence (AI) tool designed to run locally from terminals.

The new tool connects Google's Gemini AI models to local codebases, and it allows developers to make natural language requests, the company said.

READ MORE: Google introduces generative AI to Search in India, Japan

Google offers AI coding tools such as Gemini Code Assist. With the release of Gemini CLI, it competes directly with other command-line AI tools such as OpenAI's Codex CLI and Anthropic's Claude Code.

The company said it designed the tool to handle other tasks as well. Developers can tap Gemini CLI to create videos with Google's Veo 3 model, generate research reports with the company's Deep Research agent, or access real-time information through Google Search.

READ MORE: Google's Nobel prize winners stir debate over AI research

Google is also open-sourcing Gemini CLI under the Apache 2.0 license. Free users can make 60 model requests per minute and 1,000 requests per day. According to Google, it is roughly double the average number of requests developers made when using the tool.